2026-09-22

From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention

👍 4

09/18 08:00

A pretrained robot foundation policy may execute most of a long-horizon task yet repeatedly fail at a few critical subtasks. Collecting additional full-task demonstrations for supervised fine-tuning (SFT) requires operators to repeat behaviors the policy already performs well. Reinforcement learning

Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design

👍 22

09/18 08:00

Professional graphic design is a long-horizon agentic task in which structured, editable artifacts emerge from many interdependent actions, yet outcomes admit no reliable programmatic oracle. We introduce a continual adaptation framework in which a frozen frontier model operates professional design

Gricea: An Open Science Platform for Conversational AI Research

👍 5

09/18 08:00

We need studies on conversational AI (CAI) at scale to understand human behavior and shape CAI design. However, fragmented reporting of systems and study configurations hinders replication, extension, and knowledge accumulation. We present Gricea, an open-science platform representing studies as con

APort Vault: Benchmarking AI Agent Payment Authorization with the Open Agent Passport

👍 2

09/18 08:00

APort Vault is a benchmark for payment authorization in tool-using AI agents. It replays 4,371 attacks written by humans against a live payment agent during a public capture-the-flag event, across 14 models from 8 labs, five policy configurations and two replay tracks, with and without a determinist

OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue

👍 30

09/18 08:00

We define OmniVChat (Omni Video Chat) as the task of native audio-visual dialogue between a user and an omni model. In OmniVChat, omni models directly and simultaneously receive audio and video from a user and return text. The user's query is embedded in the audio and video, without a separate text

Calibrating Teacher--Student Discrepancy for On-Policy Distillation

👍 7

09/18 08:00

On-policy distillation (OPD) improves reasoning models by learning the token-level discrepancy between a stronger teacher and an on-policy student. However, this discrepancy does not purely reflect the capability gap between the teacher and the student: it also contains deviations arising from the t

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

👍 87

09/18 08:00

Training capable coding agents via reinforcement learning (RL) requires diverse tasks with reliable verifiers. Open-source codebases offer a rich source of such tasks, while existing methods typically rely on development artifacts such as issues and commits, limiting the range of tasks that can be e

GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills

👍 9

09/18 08:00

Skills can improve the performance of Large Language Model (LLM) agents by providing task-specific procedural guidance, while skill optimization further improves their effectiveness through iterative refinement. However, existing skill optimization methods typically represent skills as unstructured

RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents

👍 60

09/18 08:00

Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development through code and the command line. Real digital work requires both, interleaved rather than stacked end to end. We study hybrid CUAs that autonomously decide when to explore an interface

MintAct: A Unified Visual Agent for Digital Environments

👍 12

09/18 08:00

We present MintAct, a family of vision-language models that unifies UI grounding, multi-step navigation across mobile, desktop, and web, and visual tool use, trained at 2B, 4B, and 8B scales. Through careful design of our environments, data, and training recipes, MintAct models match the performance

Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network

👍 2

09/17 08:00

Text-guided image editing must introduce the requested changes while preserving unrelated source content. Diffusion-based editors rely on spatial controls whose inaccuracies can leave edits incomplete or alter unrelated regions. Causal autoregressive editors face a further constraint: their fixed de

Retention-Constrained Post-Training Quantization of Cellpose-SAM for Stem Cell Microscopy

👍 3

09/17 08:00

Induced pluripotent stem cell (iPSC) culture increasingly relies on segmentation foundation models, yet deployment on laboratory CPUs and edge hardware requires compression schemes that are both efficient and auditable. We present a deployment-oriented evaluation of compressed Cellpose-SAM using a p

Geometry of Values: Task Vector Composition for Ethical Preference Alignment in Language Models

👍 3

09/17 08:00

Large Language Models (LLMs) are increasingly deployed in applications that must weigh clashing moral values, yet even strong models exhibit hidden biases and brittle instruction-following across languages. We introduce a 12,000-instance dataset of two-option dilemmas covering pairwise three value c

TeleAntiFraud 2.0: A Refreshable, Profile-Grounded, and Audio-Based Benchmark for Telecom Fraud Detection

👍 4

09/17 08:00

Telecom fraud scripts evolve rapidly and are often designed to resemble routine service conversations, creating two key requirements for audio-based telecom-fraud evaluation. First, benchmarks must incorporate newly observed scam patterns without overwriting previously established test sets. Second,

Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation

👍 3

09/17 08:00

Visual signals require compact yet sufficient representations for robust downstream prediction. Convolutional sparse coding (CSC) provides an explicit mechanism for suppressing redundant components while preserving signal content, but its sparsity coefficient is typically fixed and manually selected

Paint-Anything: Unified Any-Color Control for Image Generation and Editing

👍 29

09/17 08:00

Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex value for image generation and editing. Prior work has explored color generation, editing, and colorization, but often relies on dedicated color representations or specialized inferenc

DeformSmith: Physics Harness-Guided Hierarchical Generation of Deformable Assets for Robot Manipulation

👍 3

09/17 08:00

Creating deformable assets for robot manipulation requires jointly specifying their geometry, appearance, and physical properties. This is especially challenging for deformable objects, since text and images provide limited evidence about how they deform and respond to contact, yet these responses d

When AI Reviews Train AI Reviewers: Scientific-Judgment Collapse and Mitigation

👍 5

09/17 08:00

Large language models (LLMs) increasingly participate in scientific evaluation, both as automated reviewers and as assistants to human reviewers. As model-generated reviews enter public data and future training corpora, AI peer review can become recursive: later reviewers learn from judgments produc

Self-Evolving Search Index

👍 47

09/17 08:00

Information retrieval is increasingly important as LLM agents tackle complex tasks involving diverse information needs. Because retrieval relies on an index that represents each document through index keys, retrieval quality depends heavily on how effectively these keys expose the knowledge containe

BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence

👍 12

09/16 08:00

Business intelligence (BI) is a cornerstone of enterprise decision-making and is widely used by enterprise users in software such as Power BI and Tableau. In traditional BI workflows, users need to prepare data by (1) identifying relevant tables, (2) performing data transformations, and (3) building

GAVEL: Graph World Models for Verified and Efficient Long-Horizon LLM Task Planning

👍 3

09/16 08:00

Large language models (LLMs) provide a flexible interface for long-horizon robot planning, but generated plans often fail to respect embodiment constraints, recover from planning errors, or reason effectively under partial observability. We present GAVEL, a framework for verifying and repairing long

FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection

👍 4

09/16 08:00

Large audio-language models have shown promise for anti-fraud detection by directly processing speech and reasoning over fraud-related evidence. Their deployment, however, requires predictions to follow a predefined label space and a structured decision protocol consisting of service-scenario identi

Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling

👍 29

09/16 08:00

Test-time scaling can improve large language model reasoning by generating and combining multiple candidate responses. In sampling-based methods, the inference budget is often described by the number of generated candidates, N. However, N tells us how many candidates are generated, not how they are

Verifiable Social Reasoning for LLM Assistants

👍 51

09/15 08:00

LLM assistants are widely used for daily social advice, yet evaluating their social reasoning in such consultation settings remains challenging since (i) it requires setups where the assistant learns about social situations from subjective user narratives, and (ii) social properties, such as others'

CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design

👍 5

09/14 08:00

Computer-use agents are increasingly evaluated in realistic desktop environments, but existing benchmarks provide limited coverage of professional engineering workflows whose outputs are persistent, structured artifacts. Mechanical computer-aided design (CAD) is a particularly demanding setting: an

MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup

👍 7

09/14 08:00

Scaling large language models efficiently has motivated sparse capacity mechanisms such as Mixture-of-Experts and, more recently, conditional memory: token-indexed embedding tables that augment the backbone with cheap parametric lookups. Existing memory-embedding methods retrieve via a deterministic

EvoOntology: A Self-Evolving Ontology Layer for Data Agents

👍 68

09/14 08:00

Data agents aim to fulfill natural-language instructions over heterogeneous data, including tables, files, and databases. However, data agents face a challenging agent-data gap: heterogeneous data resides outside the agent, while the agent can access it (e.g., column names and file paths) only throu

SiliconBench: Speed, Memory, and Fidelity for LLM Serving on Unified-Memory Desktops

👍 3

09/12 08:00

Concurrent local LLM serving on unified-memory desktops must preserve memory headroom and output fidelity, which speed-only rankings overlook. We introduce SiliconBench, which evaluates nine Apple Silicon serving engines through three lenses: speed, memory, and fidelity. We evaluate chat and agent s

MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads

👍 4

09/05 08:00

Multimodal Large Language Models (MLLMs) often struggle with hallucinations, thus hindering their reliable practical applications. Existing attention-based mitigation methods mainly rely on indirect signals (e.g., attention weights) that fail to accurately reflect the actual information shift underl

Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

👍 86

09/04 08:00

Reusable skills give agents transferable procedural knowledge, making scalable acquisition essential for extending agents beyond prior experience. Existing methods face two limitations: trajectory-based synthesis requires interactions with specific environments, while document-derived skills may lac

You're Already a Meat Proxy

@obie · 13.1K 粉丝 · 157.2K 阅 · 738 赞 · 98 转

09/21 05:02

I’m excited about a future that I suspect will be very hard on many long-time friends and certain people that I love. The same technology that is allowing me to be more successful than ever is

中文介绍 博主探讨未来技术对人际关系的冲击，涉及个人成功与科技发展的矛盾。

I reverse-engineered Instinct's memory. Here's exactly how it works

@DhravyaShah · 62.1K 粉丝 · 120.2K 阅 · 509 赞 · 16 转

09/21 02:49

Instinct has taken the world by storm over the last two weeks - it's one of the best imessage assistants I've used. as with every product, I decided to reverse-engineer Instinct's memory to find out

中文介绍 博主逆向工程Instinct记忆系统，解析其工作原理。

Codex vs Claude for app development

@twostraws · 120.7K 粉丝 · 77.1K 阅 · 504 赞 · 42 转

09/19 22:30

I use both Codex and Claude for app development work, both with the highest-tier subscription. Here's how I've found the two compare, plus some tips for success… TL;DR I use both agents extensively,

中文介绍 博主对比Codex和Claude在应用开发中的表现，分享使用经验与建议。

A Beginner's Guide to Jev

@omarsar0 · 320.6K 粉丝 · 73.5K 阅 · 523 赞 · 60 转

09/21 04:44

As you may have seen recently, Jev (a generalist System One model) took Twitter by storm. Many misleading examples are everywhere, but they don't really show Jev's real capabilities. Hence, we

中文介绍 博主介绍Jev模型，纠正误导性示例，展示其真实能力。

Jev, System One models, and the future of computer use

@trycua · 19.0K 粉丝 · 59.5K 阅 · 501 赞 · 39 转

09/20 06:27

What we've been building with decision models at Cua - by @ddupont808 and @francedot Over the last few days we've deprioritized some other shiny objects because we've all been Jev-crazy. TypeSafe

中文介绍 博主探讨Cua使用决策模型与Jev的未来，强调其影响。

How to Use Jev to Build a 24/7 HFT Trading System

@RohOnChain · 72.5K 粉丝 · 57.7K 阅 · 518 赞 · 54 转

09/19 22:05

I will break down the exact framework to build a millisecond speed 24/7 HFT trading system with Jev, along with the exact resources that helped me personally. Let's get straight to it. Bookmark This -

中文介绍 博主展示使用Jev构建24/7高频交易系统的框架及资源。

Jev-as-a-Judge for Agent Evals

@LangChain · 265.9K 粉丝 · 46.6K 阅 · 504 赞 · 68 转

09/20 07:31

By Daniel Shea and Seán Roche Key takeways: Jev is a fundamentally different kind of evaluator. It returns typed answers directly instead of generating text like an LLM judge. Jev was dramatically

中文介绍 介绍Jev作为评估器的独特性，返回类型化答案而非生成文本。

Jev 101: what it is, and what you can build with it

@manish_fp · 846 粉丝 · 44.1K 阅 · 512 赞 · 59 转

09/19 22:59

I have read 10+ articles, watched 5 hours of content to understand what actually Jev is and then chose to write this. It is not a chatbot, It’s a whole new kind of AI, more like a classifier which

中文介绍 博主深入解析Jev模型，区别于聊天机器人的特性。

Build your own Jev (100% local)

@_avichawla · 77.5K 粉丝 · 37.8K 阅 · 593 赞 · 80 转

09/20 14:46

Everything you need to turn an open-source LLM into a fast, local decision engine without retraining it. It covers next-token scoring, fixed choices with probability distributions, SGLang, and a

中文介绍 教程：将开源LLM转换为快速本地决策引擎，涵盖多种技术细节。

A Swarm of Fruit Flies, Building a Civilization On-Chain

@murmur_arc · 983 粉丝 · 11.8K 阅 · 553 赞 · 137 转

09/20 21:17

Prologue — No LLMs, Only Neurons This project is called murmur, and it is alive right now on Arc mainnet (Chain ID 5042), settling in real USDC. To date the flies have completed more than 23,000

中文介绍 介绍名为murmur的项目，在Arc主网上线，使用神经元而非LLM构建文明。

Jev: System One models for Prod, not God — with Diogo Almeida, CEO, TypeSafe AI

Latent Space · 09/22 06:13

The definitive Jev podcast with its lead creator.

中文介绍 Jev播客系列，由其创始人Diogo Almeida主持。

Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem

Hugging Face Blog · 09/21 21:44

中文介绍 Hugging Face Blog发布关于如何像物理学家一样修剪LLMs的文章。

Advisory Group on Mathematics and Artificial Intelligence

OpenAI News · 09/21 20:00

OpenAI is working with an independent Advisory Group on Mathematics and Artificial Intelligence to guide the review and communication of emerging AI results.

中文介绍 OpenAI与独立顾问团合作，指导数学和人工智能新兴成果的审查与传播。

Higgsfield AI ships new video features in a day with GPT-6 Astra

OpenAI News · 09/21 20:00

With GPT-6 Astra, Higgsfield AI makes video ad creation easier for small businesses and brings new creative tools to market faster.

中文介绍 Higgsfield AI利用GPT-6 Astra推出新的视频功能，简化小型企业的视频广告创作。

How we made the first comprehensive map of deaths along the US border’s “virtual wall”

MIT Tech Review AI · 09/21 20:00

Our 15-month investigation into death and surveillance along the US-Mexico border began with a simple question: Why did so many people die near government surveillance towers meant to help track and apprehend them? This story is part of Dying on Camera, a collaboration between MIT Technology Review

中文介绍 MIT Tech Review AI发布关于美国边境“虚拟墙”死亡情况的15个月调查报告。

4 ways to address the failures we found along the US border’s “virtual wall”

MIT Tech Review AI · 09/21 20:00

MIT Technology Review today published our investigation into how many people have died near the “virtual wall” of surveillance towers that the US government has installed along the US-Mexico border. We found cases of people who walked undetected through areas surveilled by advanced, AI-enabled tower

中文介绍 MIT Technology Review提出解决美国边境“虚拟墙”失败问题的四项建议。

The US spent billions on border surveillance. Why can’t it catch people before they die?

MIT Tech Review AI · 09/21 20:00

When José Morales Bernal crossed the border into the United States on April 8, 2024, the day before his 32nd birthday, it should have triggered a chain of technological alerts and human responses. As he walked through the desert in southern New Mexico that morning, he was within range of three surve

中文介绍 MIT Tech Review AI报道美国在边境监视上投入数十亿美元，却无法在人死亡前捕获他们。

She died at the San Diego border. A surveillance camera was in plain sight

MIT Tech Review AI · 09/21 20:00

She had only walked for a couple of hours, and already she was lost. It was early afternoon on Sept. 14, 2025, when 30-year-old Graciela Gómez Hernández crossed the border from the eastern edge of Tijuana into Southern California, sending voice messages to her mother and sister as she walked. This s

中文介绍 MIT Tech Review AI报道一位30岁的女性在圣地亚哥边境死亡，附近有监控摄像头。

Building standards for the next phase of AI

OpenAI News · 09/21 18:00

OpenAI outlines a path to shared global AI standards, calling for coordinated evaluation, reporting, and governance to improve safety.

中文介绍 OpenAI概述了一条走向共享全球AI标准的路径，呼吁协调评估、报告和治理以改善安全性。

Expanding OpenAI Academy with new learning paths

OpenAI News · 09/21 15:00

Explore new OpenAI Academy learning paths for employees, developers, leaders, educators, and students to build and demonstrate practical AI skills.

中文介绍 OpenAI扩展OpenAI Academy，推出新的学习路径，以构建和展示实用的AI技能。

How V7 gives AI agents institutional memory

OpenAI News · 09/21 08:00

Using GPT-5.6, V7 turns scattered company files into context agents can use to complete complex, source-linked work.

中文介绍 OpenAI的V7利用GPT-5.6将零散的公司文件转换为可供完成复杂工作的上下文代理。

tokenizers v1: encode, decode and scaling, measured

Hugging Face Blog · 09/21 08:00

中文介绍 Hugging Face Blog发布关于tokenizer v1的文章，讨论编码、解码和扩展。

Muse connectors 🤖, Meta SAM 3.1 🖼️, Gemini hacks companies 🔓

TLDR AI · 09/21 08:00

中文介绍 TLDR AI发布关于Muse连接器、Meta SAM 3.1和Gemini公司黑客的最新信息。

[AINews] Here are 6 Clones of Jev in 2 days

Latent Space · 09/19 13:48

Imitation is the sincerest form of Flattery

中文介绍 Latent Space报道Jev在两天内出现6个克隆版本。

Introducing the Australian Youth Safety Blueprint

OpenAI News · 09/18 20:00

OpenAI introduces the Australian Youth Safety Blueprint, a six-pillar roadmap for safer AI experiences that protect and empower young people.

中文介绍 OpenAI推出澳大利亚青年安全蓝图，一个包含六个支柱的路线图，以保护并赋权年轻人。